ASSET Seminar: “Learning Reliable and Robust Generative Intelligence”
April 16 at 12:00 PM - 1:15 PM
Abstract:
Robust simulation and precise modeling of physical dynamics are essential for advancing perception, planning, and control in the development of generalist physical agents. In this talk, I will present my research on building generative models that combine physical realism with scalability in high-dimensional environments. The presentation delves into both the theoretical foundations and practical implementations of our methods, including the incorporation of 3D constraints into video diffusion models and the integration of autoregressive structures into continuous generative modeling to better handle complex data. By combining these techniques, the models replicate intricate interactions in dynamic scenes and demonstrate their potential to support efficient, data-driven learning across a broad range of applications.
Zoom Link: https://upenn.zoom.us/j/92594955973
Jiatao Gu
Research Scientist/Assistant Professor
Jiatao Gu is currently a staff research scientist at Apple and an incoming Assistant Professor at the University of Pennsylvania in Fall 2025 in the CIS department. Prior to Apple, Jiatao was a senior research scientist at Facebook AI Research (FAIR). He received his Ph.D. from the University of Hong Kong after earning his Bachelor’s degree from Tsinghua University. He is the recipient of the Hong Kong PhD Fellowship. His research goal is to advance the capabilities of AI agents to interact with the physical world, with a special emphasis on leveraging generative machine learning approaches for world modeling, iterative reasoning, and effective decision-making.